Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

lasso_select

Read-only

Select the most relevant independent variables for a dependent variable using LASSO with cross-validation, AIC, or BIC, providing validated evidence for causal decision-making.

Instructions

LASSO-based variable selection. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Candidate independent variables.
`y`	Yes	Dependent variable column.
`eps`	No	Ratio of lambda_min / lambda_max.
`tol`	No	Convergence tolerance.
`seed`	No	Random seed for CV fold assignment.
`detail`	No	Payload depth: 'minimal' (~150 tokens) for sub-step calls where only the point estimate is needed; 'standard' (~1K tokens) for diagnostics + coefficient table; 'agent' (~2K tokens, default) adds violations / next_steps / suggested_functions so the LLM can plan its next call without another round-trip.	agent
`method`	No	How to choose the regularisation parameter lambda.	cv
`n_folds`	No	Number of cross-validation folds (only for ``method="cv"``).
`verbose`	No	Print progress.
`max_iter`	No	Maximum coordinate descent iterations per lambda.
`n_lambda`	No	Number of lambda values in the grid.
`as_handle`	No	If true, cache the fitted result on the server and return result_id + result_uri alongside the JSON payload so a subsequent tools/call can chain without re-running.
`data_path`	Yes	Absolute path or URL to a data file. Supported: .csv / .tsv / .txt (delimited), .parquet / .pq, .feather / .arrow, .xlsx / .xls, .dta (Stata), .json / .jsonl. Schemes: file://, s3://, gs://, https://.
`result_id`	No	Optional handle to a previously-fitted result (returned by an earlier call when as_handle=true). Tools that operate on a fitted object accept this in place of re-supplying data_path + columns.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

B3.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already establish readOnlyHint=true, so the safety profile is covered. The description adds a non-obvious 'validated evidence tier' claim that goes beyond the annotations, although it is cryptic and leaves the practical meaning of the tier unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the core purpose in the first clause. The validation-tier sentence is compact and adds context, though it could be clearer about how it should inform an agent's decision.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The rich schema and available output schema cover parameter and return semantics, so the description is minimally viable. However, for a 16-parameter statistical tool in a large sibling family, the description omits selection context and fails to explain the validation-tier phrase.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 16 parameters are documented in the input schema with types, defaults, and descriptions, so the description does not need to repeat parameter semantics. It adds no parameter detail of its own, making the schema-coverage baseline of 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly identifies the operation as 'LASSO-based variable selection,' which is a clear verb + resource statement. It does not, however, distinguish lasso_select from sibling LASSO-family tools such as rlassologit or lasso_iv.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use lasso_select instead of nearby alternatives, nor are prerequisites or exclusions stated. The validation-tier sentence does not help an agent decide between sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server